I'm Rahman, an AI Safety & ML Researcher and M.S. Computer Science student at Texas Tech University. My research focuses on LLM security, mechanistic interpretability, and adversarial ML — including work on SAEGuardBench (jailbreak detection via sparse autoencoders) and CompToolBench (compound tool-use evaluation). Previously, I worked as a Graduate Research Assistant at TransTech Transportation Lab on LiDAR processing and infrastructure safety for TxDOT. I'm looking to collaborate with teams tackling meaningful problems in AI safety, security research, and intelligent systems. Graduating August 2026 and seeking full-time roles in AI/ML research or engineering.